On 31 May 2010 23:23, teufelsdroch <[email protected]> wrote: > I'm using tesseract as part of a bigger OMR program, to recognize the > names of students. I expect to improve accuracy by handing tesseract a > list of 30 or so names from the roster: right now I'm just passing an > identical roster to lang.freq-dawg, lang.word-dawg, and lang.user- > words. > > Training with known lists makes tess a lot better, but its still > spitting out nonsense words. Is there any way to FORCE tesseract to > use one of the words in its dictionary (preferably exactly once)? > Otherwise, I'm looking at some kind of HMM post-processing and the > code is already bloated... >
It's not clear to me if you want to simply recognise a list of names, or if you want to perform 'normal' OCR including those names. -- <Leftmost> jimregan, that's because deep inside you, you are evil. <Leftmost> Also not-so-deep inside you. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To post to this group, send email to [email protected]. To unsubscribe from this group, send email to [email protected]. For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en.
